Service Mode Determination Using Intent, Emotion, and Confidence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing chatbot technologies struggle to determine the optimal service mode in real-time, leading to inappropriate service timing, degraded efficiency, and compromised customer satisfaction, especially in complex scenarios, due to reliance on single algorithms that lack scalability and adaptability.
Innovation Solution
A method and system that generates intent, emotion, and confidence parameters to determine the service mode by identifying user intent and sentiment in query content, using a combination of predefined and adaptive strategy models to seamlessly switch between model and human service modes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a single algorithm is used to determine service mode, then the system is simple to implement, but the adaptability and scalability are poor
Solution Approach 1:
The patent segments the service mode determination into multiple independent modules: intent recognition module, sentiment analysis module, confidence calculation module, and service mode selection module. Each module processes a specific aspect (user intent, emotion, confidence level) and outputs separate parameters that are later integrated. This segmentation allows the system to be highly adaptable to different scenarios while maintaining manageable complexity through modular design.
Solution Approach 2:
The patent creates a universal service mode determination system that handles multiple types of user queries and scenarios through a single multi-functional framework. The system can process various intent types (information seeking, complaint, suggestion), multiple sentiment levels, and different confidence thresholds, making it universally applicable across diverse customer service scenarios without requiring separate algorithms for each case.
2Reliability
If real-time service mode determination is implemented, then customer satisfaction improves, but computational resources and time consumption increase
Solution Approach 1:
The patent performs preliminary actions by pre-processing the user query into distinct components (intent identification, sentiment extraction, confidence calculation) before the final service mode decision. Each component is processed independently and in parallel where possible, with results stored as separate parameters. This preliminary structuring of information enables faster final decision-making and reduces the time burden of real-time processing while maintaining high service quality.
3Measurement precision
If multiple parameters are analyzed to determine service mode, then the accuracy of service mode selection improves, but the complexity of the determination process increases
Solution Approach 1:
The patent segments the multi-parameter analysis into distinct, independent calculation modules: intent recognition producing intent parameters, sentiment analysis producing emotion parameters, and similarity matching producing confidence parameters. Each module focuses on a single parameter type, making the complex determination process manageable through modular design. The segmented parameters are then integrated in a structured manner to achieve accurate service mode selection.
Solution Approach 2:
The patent transforms the complex multi-parameter determination problem into a standardized parameter framework with defined types (intent, emotion, confidence) and relationships. By establishing clear parameter definitions, calculation methods, and integration rules, the system manages determination complexity through parameter standardization while maintaining high accuracy through comprehensive multi-parameter analysis.
Data Source
AI summary
The present disclosure relates to a method, a device, and a computer program product for determining a service mode. The method includes generating an intent parameter by identifying a user intent in a query content input by a user. The method further includes generating an emotion parameter by analyzing a sentiment inclination in the query content. The method further includes generating a confidence parameter by analyzing a similarity between the query content and training data for training an adaptive strategy model. The method further includes determining a service mode for replying to the query content based on the intent parameter, the emotion parameter, and the confidence parameter. In this way, the optimal service mode can be accurately and timely determined without affecting the query process and losing information, ensuring the coherence and consistency of the user experience, thus improving the user experience.